4 resultados para Dunkl Translation Operators

em SAPIENTIA - Universidade do Algarve - Portugal


Relevância:

30.00% 30.00%

Publicador:

Resumo:

Dissertação de mest., Natural Language Processing & Human Language Technology, Faculdade de Ciências Humanas e Sociais, Univ. do Algarve, 2011

Relevância:

20.00% 20.00%

Publicador:

Resumo:

End-stopped cells in cortical area V1, which combine out- puts of complex cells tuned to different orientations, serve to detect line and edge crossings (junctions) and points with a large curvature. In this paper we study the importance of the multi-scale keypoint representa- tion, i.e. retinotopic keypoint maps which are tuned to different spatial frequencies (scale or Level-of-Detail). We show that this representation provides important information for Focus-of-Attention (FoA) and object detection. In particular, we show that hierarchically-structured saliency maps for FoA can be obtained, and that combinations over scales in conjunction with spatial symmetries can lead to face detection through grouping operators that deal with keypoints at the eyes, nose and mouth, especially when non-classical receptive field inhibition is employed. Al- though a face detector can be based on feedforward and feedback loops within area V1, such an operator must be embedded into dorsal and ventral data streams to and from higher areas for obtaining translation-, rotation- and scale-invariant face (object) detection.

Relevância:

20.00% 20.00%

Publicador:

Resumo:

The present dissertation examines how grammatical aspect and mood are handled by machine translation (MT) systems within the scope of imperative sentences (orders, recommendations) when dealing with the language pair French-Greek (unidirectional, towards Greek). As the grammatical category of aspect is not expressed in the same way in both languages, choosing the correct aspect value when translating a verb from French to Greek can pose problems. We are interested in describing the types of errors that occur and their frequency in a corpus taken from texts pertaining to the security domain and from technical manuals, where imperative sentences are very common. In order to further delimit our research, our sample consists of sentences that comply with the general principles of simplicity and readability provided by several controlled language guidelines and aimed at higher translatability when having MT in mind. In a second phase, this study aims at discovering how modifying some of the control rules would help (or not) the MT systems better decide upon the translation of aspect and mood.

Relevância:

20.00% 20.00%

Publicador:

Resumo:

Dissertação de mestrado, Estudos Literários e Artísticos, Faculdade de Ciências Humanas e Sociais, Universidade do Algarve, 2015